arXiv subjects

Yang Li

Publications and source records attributed to Yang Li.

At least 505 records · Page 28Linked to original sources

arXiv2025

Towards Solving More Challenging IMO Problems via Decoupled Reasoning and Proving

Automated Theorem Proving (ATP) in formal languages is a foundational challenge for AI. While Large Language Models (LLMs) have driven remarkable progress, a significant gap remains between their powerful informal reasoning capabilities and their weak formal proving performance. Recent studies show that the informal accuracy exceeds 80% while formal success remains below 8% on benchmarks like PutnamBench. We argue this gap persists because current state-of-the-art provers, by tightly coupling reasoning and proving, are trained with paradigms that inadvertently punish deep reasoning in favor of shallow, tactic-based strategies. To bridge this fundamental gap, we propose a novel framework that decouples high-level reasoning from low-level proof generation. Our approach utilizes two distinct, specialized models: a powerful, general-purpose Reasoner to generate diverse, strategic subgoal lemmas, and an efficient Prover to rigorously verify them. This modular design liberates the model's full reasoning potential and bypasses the pitfalls of end-to-end training. We evaluate our method on a challenging set of post-2000 IMO problems, a problem set on which no prior open-source prover has reported success. Our decoupled framework successfully solves 5 of these problems, demonstrating a significant step towards automated reasoning on exceptionally difficult mathematical challenges. To foster future research, we release our full dataset of generated and verified lemmas for a wide range of IMO problems, available at https://tencent-imo.github.io/ .

cs.LO↗

arXiv2025

Observer-Based Distributed Model Predictive Control for String-Stable Multi-vehicle Systems with Markovian Switching Topology

Switching communication topologies can cause instability in vehicle platoons, as vehicle information may be lost during the dynamic switching process. This highlights the need to design a controller capable of maintaining the stability of vehicle platoons under dynamically changing topologies. However, capturing the dynamic characteristics of switching topologies and obtaining complete vehicle information for controller design while ensuring stability remains a significant challenge. In this study, we propose an observer-based distributed model predictive control (DMPC) method for vehicle platoons under directed Markovian switching topologies. Considering the stochastic nature of the switching topologies, we model the directed switching communication topologies using a continuous-time Markov chain. To obtain the leader vehicle's information for controller design, we develop a fully distributed adaptive observer that can quickly adapt to the randomly switching topologies, ensuring that the observed information is not affected by the dynamic topology switches. Additionally, a sufficient condition is derived to guarantee the mean-square stability of the observer. Furthermore, we construct the DMPC terminal update law based on the observer and formulate a string stability constraint based on the observed information. Numerical simulations demonstrate that our method can reduce tracking errors while ensuring string stability.

eess.SY↗

arXiv2025

Understanding Knowledge Transferability for Transfer Learning: A Survey

Transfer learning has become an essential paradigm in artificial intelligence, enabling the transfer of knowledge from a source task to improve performance on a target task. This approach, particularly through techniques such as pretraining and fine-tuning, has seen significant success in fields like computer vision and natural language processing. However, despite its widespread use, how to reliably assess the transferability of knowledge remains a challenge. Understanding the theoretical underpinnings of each transferability metric is critical for ensuring the success of transfer learning. In this survey, we provide a unified taxonomy of transferability metrics, categorizing them based on transferable knowledge types and measurement granularity. This work examines the various metrics developed to evaluate the potential of source knowledge for transfer learning and their applicability across different learning paradigms emphasizing the need for careful selection of these metrics. By offering insights into how different metrics work under varying conditions, this survey aims to guide researchers and practitioners in selecting the most appropriate metric for specific applications, contributing to more efficient, reliable, and trustworthy AI systems. Finally, we discuss some open challenges in this field and propose future research directions to further advance the application of transferability metrics in trustworthy transfer learning.

cs.LG↗

arXiv2025

NaturalThoughts: Selecting and Distilling Reasoning Traces for General Reasoning Tasks

Recent work has shown that distilling reasoning traces from a larger teacher model via supervised finetuning outperforms reinforcement learning with the smaller student model alone (Guo et al. 2025). However, there has not been a systematic study of what kind of reasoning demonstrations from the teacher are most effective in improving the student model's reasoning capabilities. In this work we curate high-quality "NaturalThoughts" by selecting reasoning traces from a strong teacher model based on a large pool of questions from NaturalReasoning (Yuan et al. 2025). We first conduct a systematic analysis of factors that affect distilling reasoning capabilities, in terms of sample efficiency and scalability for general reasoning tasks. We observe that simply scaling up data size with random sampling is a strong baseline with steady performance gains. Further, we find that selecting difficult examples that require more diverse reasoning strategies is more sample-efficient to transfer the teacher model's reasoning skills. Evaluated on both Llama and Qwen models, training with NaturalThoughts outperforms existing reasoning datasets such as OpenThoughts, LIMO, etc. on general STEM reasoning benchmarks including GPQA-Diamond, MMLU-Pro and SuperGPQA.

cs.CL↗

arXiv2025

Volumetric segmentation of muscle compartments using in vivo imaging and architectural validation in human finger flexors

Segmenting muscle compartments and measuring their architecture can facilitate movement function assessment, accurate musculoskeletal modeling, and synergy-based electromyogram simulation. Here, we presented a novel method for volumetric segmentation of muscle compartments using in vivo imaging, focusing on the independent compartments for finger control of flexor digitorum superficialis (FDS). Besides, we measured the architectural properties of FDS compartments and validated the segmentation. Specifically, ultrasound and magnetic resonance imaging (MRI) from 10 healthy subjects were used for segmentation and measurement, while electromyography was utilized for validation. A two-step piecewise segmentation was proposed, first annotating compartment regions in the cross-sectional ultrasound image based on compartment movement, and then performing minimum energy matching to register the ultrasound data to the three-dimensional MRI coordinate system. Additionally, the architectural properties were measured in the compartment masks from the segmentation using MRI tractography. Anatomical correctness was verified by comparing known anatomy with reconstructed fiber tracts and measured properties, while segmentation accuracy was quantified as the percentage of finger electromyogram centers falling within their corresponding compartments. Results demonstrated agreement for the fiber orientation between the tractography and cadaveric photographs. Significant differences in architectural properties (P < 0.001) were observed between compartments. The properties of FDS and its compartments were within the physiological ranges (P < 0.01). 95% (38/40) of the electromyogram centers were located within respective compartments, with 2 errors occurring in the index and little fingers. The validated segmentation method and derived architectural properties may advance biomedical applications.

eess.IV↗

arXiv2025

Ovis-U1 Technical Report

In this report, we introduce Ovis-U1, a 3-billion-parameter unified model that integrates multimodal understanding, text-to-image generation, and image editing capabilities. Building on the foundation of the Ovis series, Ovis-U1 incorporates a diffusion-based visual decoder paired with a bidirectional token refiner, enabling image generation tasks comparable to leading models like GPT-4o. Unlike some previous models that use a frozen MLLM for generation tasks, Ovis-U1 utilizes a new unified training approach starting from a language model. Compared to training solely on understanding or generation tasks, unified training yields better performance, demonstrating the enhancement achieved by integrating these two tasks. Ovis-U1 achieves a score of 69.6 on the OpenCompass Multi-modal Academic Benchmark, surpassing recent state-of-the-art models such as Ristretto-3B and SAIL-VL-1.5-2B. In text-to-image generation, it excels with scores of 83.72 and 0.89 on the DPG-Bench and GenEval benchmarks, respectively. For image editing, it achieves 4.00 and 6.42 on the ImgEdit-Bench and GEdit-Bench-EN, respectively. As the initial version of the Ovis unified model series, Ovis-U1 pushes the boundaries of multimodal understanding, generation, and editing.

cs.CV↗

arXiv2025

UAVD-Mamba: Deformable Token Fusion Vision Mamba for Multimodal UAV Detection

Unmanned Aerial Vehicle (UAV) object detection has been widely used in traffic management, agriculture, emergency rescue, etc. However, it faces significant challenges, including occlusions, small object sizes, and irregular shapes. These challenges highlight the necessity for a robust and efficient multimodal UAV object detection method. Mamba has demonstrated considerable potential in multimodal image fusion. Leveraging this, we propose UAVD-Mamba, a multimodal UAV object detection framework based on Mamba architectures. To improve geometric adaptability, we propose the Deformable Token Mamba Block (DTMB) to generate deformable tokens by incorporating adaptive patches from deformable convolutions alongside normal patches from normal convolutions, which serve as the inputs to the Mamba Block. To optimize the multimodal feature complementarity, we design two separate DTMBs for the RGB and infrared (IR) modalities, with the outputs from both DTMBs integrated into the Mamba Block for feature extraction and into the Fusion Mamba Block for feature fusion. Additionally, to improve multiscale object detection, especially for small objects, we stack four DTMBs at different scales to produce multiscale feature representations, which are then sent to the Detection Neck for Mamba (DNM). The DNM module, inspired by the YOLO series, includes modifications to the SPPF and C3K2 of YOLOv11 to better handle the multiscale features. In particular, we employ cross-enhanced spatial attention before the DTMB and cross-channel attention after the Fusion Mamba Block to extract more discriminative features. Experimental results on the DroneVehicle dataset show that our method outperforms the baseline OAFA method by 3.6% in the mAP metric. Codes will be released at https://github.com/GreatPlum-hnu/UAVD-Mamba.git.

cs.CV↗

arXiv2025

Brain-inspired and Self-based Artificial Intelligence

The question "Can machines think?" and the Turing Test to assess whether machines could achieve human-level intelligence is one of the roots of AI. With the philosophical argument "I think, therefore I am", this paper challenge the idea of a "thinking machine" supported by current AIs since there is no sense of self in them. Current artificial intelligence is only seemingly intelligent information processing and does not truly understand or be subjectively aware of oneself and perceive the world with the self as human intelligence does. In this paper, we introduce a Brain-inspired and Self-based Artificial Intelligence (BriSe AI) paradigm. This BriSe AI paradigm is dedicated to coordinating various cognitive functions and learning strategies in a self-organized manner to build human-level AI models and robotic applications. Specifically, BriSe AI emphasizes the crucial role of the Self in shaping the future AI, rooted with a practical hierarchical Self framework, including Perception and Learning, Bodily Self, Autonomous Self, Social Self, and Conceptual Self. The hierarchical framework of the Self highlights self-based environment perception, self-bodily modeling, autonomous interaction with the environment, social interaction and collaboration with others, and even more abstract understanding of the Self. Furthermore, the positive mutual promotion and support among multiple levels of Self, as well as between Self and learning, enhance the BriSe AI's conscious understanding of information and flexible adaptation to complex environments, serving as a driving force propelling BriSe AI towards real Artificial General Intelligence.

cs.AI↗

arXiv2025

Continual Adaptation: Environment-Conditional Parameter Generation for Object Detection in Dynamic Scenarios

In practice, environments constantly change over time and space, posing significant challenges for object detectors trained based on a closed-set assumption, i.e., training and test data share the same distribution. To this end, continual test-time adaptation has attracted much attention, aiming to improve detectors' generalization by fine-tuning a few specific parameters, e.g., BatchNorm layers. However, based on a small number of test images, fine-tuning certain parameters may affect the representation ability of other fixed parameters, leading to performance degradation. Instead, we explore a new mechanism, i.e., converting the fine-tuning process to a specific-parameter generation. Particularly, we first design a dual-path LoRA-based domain-aware adapter that disentangles features into domain-invariant and domain-specific components, enabling efficient adaptation. Additionally, a conditional diffusion-based parameter generation mechanism is presented to synthesize the adapter's parameters based on the current environment, preventing the optimization from getting stuck in local optima. Finally, we propose a class-centered optimal transport alignment method to mitigate catastrophic forgetting. Extensive experiments conducted on various continuous domain adaptive object detection tasks demonstrate the effectiveness. Meanwhile, visualization results show that the representation extracted by the generated parameters can capture more object-related information and strengthen the generalization ability.

cs.CV↗

arXiv2025

Narrow beam and low-sidelobe two-dimensional beam steering on thin-film lithium niobate optical phased array

Optical beam steering has become indispensable in free-space optical communications, light detection and ranging (LiDAR), mapping, and projection. Optical phased array (OPA) leads this field, yet conventional versions still suffer from a narrow steering field of view (FOV), insufficient sidelobe suppression, and limited angular resolution. Thin-film lithium niobate (LN), with its strong Pockels electro-optic (EO) effect, offers a powerful integrated-photonics platform to overcome these limitations. Here we present a two-dimensional (2D) EO-steered OPA based on a non-uniformly spaced X-cut thin-film LN ridge-waveguide array. A superlattice ridge design suppresses optical crosstalk to -20 dB, enabling low-sidelobe far-field radiation. Using particle swarm optimization (PSO) method, we transform a uniformly spaced array into an optimized non-uniform design, largely improving angular resolution while maintaining sidelobe suppression. When combined with a single-radiating trapezoidal end-fire emitter incorporating an etched grating, the device produces a main-lobe beam width of 0.99 degree*0.63 degree from an aperture of only 140 um*250 um, achieving a wide 2D steering range of 47 degree*9.36 degree with a 20 dB sidelobe-suppression ratio. These results highlight thin-film LN OPA as a compelling route toward heterogeneous, compact, and high-performance EO beam-steering modules and ultra-miniaturized optical modulators.

physics.optics↗

arXiv2025

Mixture of Experts-augmented Deep Unfolding for Activity Detection in IRS-aided Systems

In the realm of activity detection for massive machine-type communications, intelligent reflecting surfaces (IRS) have shown significant potential in enhancing coverage for devices lacking direct connections to the base station (BS). However, traditional activity detection methods are typically designed for a single type of channel model, which does not reflect the complexities of real-world scenarios, particularly in systems incorporating IRS. To address this challenge, this paper introduces a novel approach that combines model-driven deep unfolding with a mixture of experts (MoE) framework. By automatically selecting one of three expert designs and applying it to the unfolded projected gradient method, our approach eliminates the need for prior knowledge of channel types between devices and the BS. Simulation results demonstrate that the proposed MoE-augmented deep unfolding method surpasses the traditional covariance-based method and black-box neural network design, delivering superior detection performance under mixed channel fading conditions.

cs.LG↗

arXiv2025

Kimi-VL Technical Report

We present Kimi-VL, an efficient open-source Mixture-of-Experts (MoE) vision-language model (VLM) that offers advanced multimodal reasoning, long-context understanding, and strong agent capabilities - all while activating only 2.8B parameters in its language decoder (Kimi-VL-A3B). Kimi-VL demonstrates strong performance across challenging domains: as a general-purpose VLM, Kimi-VL excels in multi-turn agent tasks (e.g., OSWorld), matching flagship models. Furthermore, it exhibits remarkable capabilities across diverse challenging vision language tasks, including college-level image and video comprehension, OCR, mathematical reasoning, and multi-image understanding. In comparative evaluations, it effectively competes with cutting-edge efficient VLMs such as GPT-4o-mini, Qwen2.5-VL-7B, and Gemma-3-12B-IT, while surpassing GPT-4o in several key domains. Kimi-VL also advances in processing long contexts and perceiving clearly. With a 128K extended context window, Kimi-VL can process diverse long inputs, achieving impressive scores of 64.5 on LongVideoBench and 35.1 on MMLongBench-Doc. Its native-resolution vision encoder, MoonViT, further allows it to see and understand ultra-high-resolution visual inputs, achieving 83.2 on InfoVQA and 34.5 on ScreenSpot-Pro, while maintaining lower computational cost for common tasks. Building upon Kimi-VL, we introduce an advanced long-thinking variant: Kimi-VL-Thinking-2506. Developed through long chain-of-thought (CoT) supervised fine-tuning (SFT) and reinforcement learning (RL), the latest model exhibits strong long-horizon reasoning capabilities (64.0 on MMMU, 46.3 on MMMU-Pro, 56.9 on MathVision, 80.1 on MathVista, 65.2 on VideoMMMU) while obtaining robust general abilities. Code and models are publicly accessible at https://github.com/MoonshotAI/Kimi-VL.

cs.CV↗

arXiv2025

Auto-Regressive Surface Cutting

Surface cutting is a fundamental task in computer graphics, with applications in UV parameterization, texture mapping, and mesh decomposition. However, existing methods often produce technically valid but overly fragmented atlases that lack semantic coherence. We introduce SeamGPT, an auto-regressive model that generates cutting seams by mimicking professional workflows. Our key technical innovation lies in formulating surface cutting as a next token prediction task: sample point clouds on mesh vertices and edges, encode them as shape conditions, and employ a GPT-style transformer to sequentially predict seam segments with quantized 3D coordinates. Our approach achieves exceptional performance on UV unwrapping benchmarks containing both manifold and non-manifold meshes, including artist-created, and 3D-scanned models. In addition, it enhances existing 3D segmentation tools by providing clean boundaries for part decomposition.

cs.GR↗

arXiv2025

Relativistic dynamics of charmonia in strong magnetic fields

We investigate the properties of charmonium systems in strong external magnetic fields using a relativistic light-front Hamiltonian approach within the Basis Light-Front Quantization (BLFQ) framework. By solving the eigenvalue problem for the invariant mass squared operator with confinement potentials and one-gluon-exchange interactions, we obtain the mass spectrum and wave functions under varying magnetic fields. Our results reveal significant spectral modifications via the Zeeman effect, including $η_c$-$J/ψ$ mixing and magnetic sublevel splitting. Momentum density analysis demonstrates wave function deformation, with transverse momentum broadening and longitudinal narrowing under strong fields, alongside structural shifts in parton distributions such as double-hump profiles in excited states. Relativistic corrections and center-of-mass coupling critically drive these dynamics, highlighting the necessity of a relativistic framework for QCD bound states in extreme magnetic environments.

hep-ph↗

arXiv2025

Ring-lite: Scalable Reasoning via C3PO-Stabilized Reinforcement Learning for LLMs

We present Ring-lite, a Mixture-of-Experts (MoE)-based large language model optimized via reinforcement learning (RL) to achieve efficient and robust reasoning capabilities. Built upon the publicly available Ling-lite model, a 16.8 billion parameter model with 2.75 billion activated parameters, our approach matches the performance of state-of-the-art (SOTA) small-scale reasoning models on challenging benchmarks (e.g., AIME, LiveCodeBench, GPQA-Diamond) while activating only one-third of the parameters required by comparable models. To accomplish this, we introduce a joint training pipeline integrating distillation with RL, revealing undocumented challenges in MoE RL training. First, we identify optimization instability during RL training, and we propose Constrained Contextual Computation Policy Optimization(C3PO), a novel approach that enhances training stability and improves computational throughput via algorithm-system co-design methodology. Second, we empirically demonstrate that selecting distillation checkpoints based on entropy loss for RL training, rather than validation metrics, yields superior performance-efficiency trade-offs in subsequent RL training. Finally, we develop a two-stage training paradigm to harmonize multi-domain data integration, addressing domain conflicts that arise in training with mixed dataset. We will release the model, dataset, and code.

cs.CL↗

arXiv2025

KG-FGNN: Knowledge-guided GNN Foundation Model for Fertilisation-oriented Soil GHG Flux Prediction

Precision soil greenhouse gas (GHG) flux prediction is essential in agricultural systems for assessing environmental impacts, developing emission mitigation strategies and promoting sustainable agriculture. Due to the lack of advanced sensor and network technologies on majority of farms, there are challenges in obtaining comprehensive and diverse agricultural data. As a result, the scarcity of agricultural data seriously obstructs the application of machine learning approaches in precision soil GHG flux prediction. This research proposes a knowledge-guided graph neural network framework that addresses the above challenges by integrating knowledge embedded in an agricultural process-based model and graph neural network techniques. Specifically, we utilise the agricultural process-based model to simulate and generate multi-dimensional agricultural datasets for 47 countries that cover a wide range of agricultural variables. To extract key agricultural features and integrate correlations among agricultural features in the prediction process, we propose a machine learning framework that integrates the autoencoder and multi-target multi-graph based graph neural networks, which utilises the autoencoder to selectively extract significant agricultural features from the agricultural process-based model simulation data and the graph neural network to integrate correlations among agricultural features for accurately predict fertilisation-oriented soil GHG fluxes. Comprehensive experiments were conducted with both the agricultural simulation dataset and real-world agricultural dataset to evaluate the proposed approach in comparison with well-known baseline and state-of-the-art regression methods. The results demonstrate that our proposed approach provides superior accuracy and stability in fertilisation-oriented soil GHG prediction.

cs.LG↗

arXiv2025

MMWiLoc: A Multi-Sensor Dataset and Robust Device-Free Localization Method Using Commercial Off-The-Shelf Millimeter Wave Wi-Fi Devices

Device-free Wi-Fi sensing has numerous benefits in practical settings, as it eliminates the requirement for dedicated sensing devices and can be accomplished using current low-cost Wi-Fi devices. With the development of Wi-Fi standards, millimeter wave Wi-Fi devices with 60GHz operating frequency and up to 4GHz bandwidth have become commercially available. Although millimeter wave Wi-Fi presents great promise for Device-Free Wi-Fi sensing with increased bandwidth and beam-forming ability, there still lacks a method for localization using millimeter wave Wi-Fi. Here, we present two major contributions: First, we provide a comprehensive multi-sensor dataset that synchronously captures human movement data from millimeter wave Wi-Fi, 2.4GHz Wi-Fi, and millimeter wave radar sensors. This dataset enables direct performance comparisons across different sensing modalities and facilitates reproducible researches in indoor localization. Second, we introduce MMWiLoc, a novel localization method that achieves centimeter-level precision with low computational cost. MMWiLoc incorporates two components: beam pattern calibration using Expectation Maximization and target localization through Multi-Scale Compression Sensing. The system processes beam Signal-to-Noise Ratio (beamSNR) information from the beam-forming process to determine target Angle of Arrival (AoA), which is then fused across devices for localization. Our extensive evaluation demonstrates that MMWiLoc achieves centimeter-level precision, outperforming 2.4GHz Wi-Fi systems while maintaining competitive performance with high-precision radar systems. The dataset and examples processing code will be released after this paper is accepted at https://github.com/wowoyoho/MMWiLoc.

eess.SP↗

arXiv2025

Shapley Machine: A Game-Theoretic Framework for N-Agent Ad Hoc Teamwork

Open multi-agent systems are increasingly important in modeling real-world applications, such as smart grids, swarm robotics, etc. In this paper, we aim to investigate a recently proposed problem for open multi-agent systems, referred to as n-agent ad hoc teamwork (NAHT), where only a number of agents are controlled. Existing methods tend to be based on heuristic design and consequently lack theoretical rigor and ambiguous credit assignment among agents. To address these limitations, we model and solve NAHT through the lens of cooperative game theory. More specifically, we first model an open multi-agent system, characterized by its value, as an instance situated in a space of cooperative games, generated by a set of basis games. We then extend this space, along with the state space, to accommodate dynamic scenarios, thereby characterizing NAHT. Exploiting the justifiable assumption that basis game values correspond to a sequence of n-step returns with different horizons, we represent the state values for NAHT in a form similar to $λ$-returns. Furthermore, we derive Shapley values to allocate state values to the controlled agents, as credits for their contributions to the ad hoc team. Different from the conventional approach to shaping Shapley values in an explicit form, we shape Shapley values by fulfilling the three axioms uniquely describing them, well defined on the extended game space describing NAHT. To estimate Shapley values in dynamic scenarios, we propose a TD($λ$)-like algorithm. The resulting reinforcement learning (RL) algorithm is referred to as Shapley Machine. To our best knowledge, this is the first time that the concepts from cooperative game theory are directly related to RL concepts. In experiments, we demonstrate the effectiveness of Shapley Machine and verify reasonableness of our theory.

cs.MA↗